Assessment and Monitoring of Students Employability in IT Industry Using Machine Learning: A Comparative Study with Data Science Approach

Student Placement is an essential objective for academic institutions, as their reputation and annual enrollment are closely tied to successful campus placements. Institutions dedicate extensive effort to enhancing student employability. This study intends to predict student placements by analyzing previous years’ placement data. It is not only predicting placement outcomes but also identifies the appropriate machine learning algorithm to ensure reliable and accurate predictions. This article studied Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, K-Nearest Neighbor, Gradient Boosting models for placement prediction based on previous years students’ records. The models effectively calculate placement probabilities and generate useful decision-making insights. The performance of the models are evaluated based on dataset’s quality. This predictive tool guide training and Placement Department in recognizing students with higher employability potential for enhancing their technical and soft skills. Furthermore, this prediction models serves as a useful self-assessment tool for students helping them understand their placement aspect and prepare accordingly. This paper presents a comparison on statistical placement prediction models, particularly focusing on final year engineering students.